© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22293
    Prev
    Next
    INDEX
    Explanations

    v followed by country

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主è§Ĵ
    -0.08
    åĴĮæĻ®éĢļ
    -0.07
    ä¸Ńæĸ¹
    -0.07
    ä¸İåĽ½åĨħ
    -0.07
    ukkan
    -0.06
    ä¸İæĻ®éĢļ
    -0.06
    å°ıåѦèĭ±è¯Ń
    -0.06
    主人åħ¬
    -0.06
    楷
    -0.06
    漪
    -0.06
    POSITIVE LOGITS
    éĢģèµ°
    0.07
    ä¸įæ³ķåĪĨåŃIJ
    0.07
    _plugins
    0.07
    apur
    0.07
    ç¿ģ
    0.07
    -describedby
    0.06
    水产åĵģ
    0.06
    .Extension
    0.06
     Nev
    0.06
    åħĭç¦ı
    0.06
    Activations Density 0.999%

    No Known Activations